• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.4
• /
• pp.24-38
• /
• 2019

Due to the dramatic spatial changes caused by industrialization, environmental problems such as air pollution and urban heat island phenomenon, etc. are occurring in cities. In this case, the wind corridor, which is a passage through which fresh and cool air generated in forests outside cities move to the downtown, can be used as a spatial planning method for improving urban environmental problems. Cold air is determined by the characteristics of the flow depending on the topography and land use of cities, and based on this, the medium- and long-term plan should be established. Therefore, this study analyzed the flow of cold air at night through the KLAM_21 model in Suwon-si, Gyeonggi-do, to prepare the basic data required to apply the wind corridors. As a result, it turned out that cold air of Suwon-si was mainly generated from Gwanggyo Mountain that is a large mountain area in the north, and flowed into the urbanization promotion area, and about three hours after sunset, cold air flowed into the downtown. By district, the depth, wind speed, and direction of the cold air layer were formed differently according to the characteristics of the topography and land use. In the areas where large forests were adjacent, the flow of cold air was active. There are three main wind corridors where cold air flows to the downtown of Suwon-si, all of which are formed around rivers. Especially, if the connection between rivers and the surrounding green areas is high, the effect of wind corridors is found to be significant. In order to utilize the wind corridors of Suwon-si, based on the results of this study, it is necessary to make climate maps through actual survey and complex analysis of cold air flow and establish mid-to-long-term plans for the conservation and expansion of major wind corridors.

• Journal of Wetlands Research
• /
• v.6 no.3
• /
• pp.55-70
• /
• 2004

The wetland ecosystem is a complex products of various erosion force, accumulation as water flows, hydrogeomorphic units, seasonal changes, the amount of rainfalls, and other essential element. There is no single, correct, ecologically sound definition for wetlands because of the diversity of wetlands and the demarcation between dry and wet environments occurs along a continuum, but wetland plays various ecosystem functions. Despite comprehensive integration through classification and impact factors there is still lacking in systematic management of wetlands. Classification system developed by the USFWS(1979) is hierarchical progresses from systems and subsystems at general levels to classes, subclasses, dominance types, and habitat modifiers. Systems and subsystems are delineated according to major physical attributes such as tidal flushing, ocean-derived salts, and the energy of flowing water or waves. Classes and subclasses describe the type of substrate and habitat or the physiognomy of the vegetation or faunal assemblage. Wetland classes are divided into physical types and biotic types. For the wise management of wetlands in Korea, this study was carried out to examine methodology of USFWS classification system and discuss its application for Korean wetland hydrogeomorphic units already known. Seven wetland types were chosen as study sites in Korea divided into some different types based on USFWS system. Three wetland types belonging to palustrine system showed no difference between Wangdungjae wetland and Mujechi wetland, but Youngnup of Mt. Daeam was different from the former two types at the level of dominant types. This fact means that setting of classification system for management of wetland is needed. Although we may never know much about the wetland resources that have been lost, there are opportunities to conserve the riches that remain. Extensive inventory of all wetland types and documentation of their ecosystem functions are vital. Unique and vulnerable examples in particular need to be identified and protected. Furthermore, a framework with which to demonstrate wetland characteristics and relationships is needed that is sufficiently detailed to achieve the identification of the integrity and salient features of an enormous range of wetland types.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.